Skip to main content

Yellhorn MCP server uses Gemini 2.5 pro to generate detailed work plans and review pull requests.

Project description

Yellhorn MCP

Yellhorn Logo

A Model Context Protocol (MCP) server that exposes Gemini 2.5 Pro capabilities to Claude Code for software development tasks.

Features

  • Generate Work Plans: Creates GitHub issues with detailed implementation plans based on your codebase, with customizable title and detailed description
  • Review Code Diffs: Evaluates pull requests against the original work plan with full codebase context and provides detailed feedback
  • Seamless GitHub Integration: Automatically creates labeled issues, posts reviews as PR comments with references to original issues, and handles asynchronous processing

Installation

# Install from PyPI
pip install yellhorn-mcp

# Install from source
git clone https://github.com/msnidal/yellhorn-mcp.git
cd yellhorn-mcp
pip install -e .

Configuration

The server requires the following environment variables:

  • GEMINI_API_KEY: Your Gemini API key (required)
  • REPO_PATH: Path to your repository (defaults to current directory)
  • YELLHORN_MCP_MODEL: Gemini model to use (defaults to "gemini-2.5-pro-exp-03-25")

The server also requires the GitHub CLI (gh) to be installed and authenticated.

Usage

Running the server

# As a standalone server
yellhorn-mcp --repo-path /path/to/repo --host 127.0.0.1 --port 8000

# Using the MCP CLI
mcp dev yellhorn_mcp.server

# Install as a permanent MCP server for Claude Desktop
mcp install yellhorn_mcp.server

# Set environment variables during installation
mcp install yellhorn_mcp.server -v GEMINI_API_KEY=your_key_here -v REPO_PATH=/path/to/repo

Integration with Claude Code

When working with Claude Code, you can use the Yellhorn MCP tools by:

  1. Starting a project task:

    Please generate a work plan with title "[Your Title]" and detailed description "[Your detailed requirements]"
    
  2. Reviewing your implementation:

    Please review my changes in PR [PR URL] against the work plan from [GitHub issue URL]
    

Tools

generate_work_plan

Creates a GitHub issue with a detailed work plan based on the title and detailed description, labeled with 'yellhorn-mcp'.

Input:

  • title: Title for the GitHub issue (will be used as issue title and header)
  • detailed_description: Detailed description for the workplan

Output:

  • URL to the created GitHub issue

review_work_plan

Reviews a pull request against the original work plan and provides feedback. Includes the full codebase as context for better analysis and adds a reference to the original work plan in the review comment.

Input:

  • work_plan_issue_url: GitHub issue URL containing the work plan
  • pull_request_url: GitHub PR URL containing the changes to review
  • ctx: Server context

Output:

  • Asynchronously posts a review directly to the PR with a reference to the original work plan issue

Development

# Install development dependencies
pip install -e ".[dev]"

# Run tests
pytest

CI/CD

The project uses GitHub Actions for continuous integration and deployment:

  • Testing: Runs automatically on pull requests and pushes to the main branch

    • Linting with flake8
    • Format checking with black
    • Testing with pytest
  • Publishing: Automatically publishes to PyPI when a version tag is pushed

    • Tag must match the version in pyproject.toml (e.g., v0.1.4)
    • Requires a PyPI API token stored as a GitHub repository secret (PYPI_API_TOKEN)

To release a new version:

  1. Update version in pyproject.toml
  2. Commit changes: git commit -am "Bump version to X.Y.Z"
  3. Tag the commit: git tag vX.Y.Z
  4. Push changes and tag: git push && git push --tags

For more detailed instructions, see the Usage Guide.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

yellhorn_mcp-0.1.4.tar.gz (1.1 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

yellhorn_mcp-0.1.4-py3-none-any.whl (10.1 kB view details)

Uploaded Python 3

File details

Details for the file yellhorn_mcp-0.1.4.tar.gz.

File metadata

  • Download URL: yellhorn_mcp-0.1.4.tar.gz
  • Upload date:
  • Size: 1.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for yellhorn_mcp-0.1.4.tar.gz
Algorithm Hash digest
SHA256 c5054891816b774915bbb5b8b3297797c943d57d2b3cddb0c736688f6b5acb3d
MD5 69bfa740ab816a1c538a34d1afb52c2e
BLAKE2b-256 df29025663abf944229a0778fa3c2d152475bb0fca2fba366f4910427acadd79

See more details on using hashes here.

File details

Details for the file yellhorn_mcp-0.1.4-py3-none-any.whl.

File metadata

  • Download URL: yellhorn_mcp-0.1.4-py3-none-any.whl
  • Upload date:
  • Size: 10.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for yellhorn_mcp-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 d7970a22e4acaebedee9238bf1c93ca2acd32d820246c3f05f92189795e2c9e4
MD5 ea963802dd06582c74ba8f8c58c9c85f
BLAKE2b-256 a14901a55010242274426fa69eda4706e90fe0a765c0607fd039879f2be73698

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page